Score: 1

Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling

Published: August 22, 2025 | arXiv ID: 2508.16745v1

By: Ivan Rodkin , Daniil Orel , Konstantin Smirnov and more

Potential Business Impact:

Makes computers better at thinking through problems.

Business Areas:
Machine Learning Artificial Intelligence, Data and Analytics, Software

Reasoning is a core capability of large language models, yet understanding how they learn and perform multi-step reasoning remains an open problem. In this study, we explore how different architectures and training methods affect model multi-step reasoning capabilities within a cellular automata framework. By training on state sequences generated with random Boolean functions for random initial conditions to exclude memorization, we demonstrate that most neural architectures learn to abstract the underlying rules. While models achieve high accuracy in next-state prediction, their performance declines sharply if multi-step reasoning is required. We confirm that increasing model depth plays a crucial role for sequential computations. We demonstrate that an extension of the effective model depth with recurrence, memory, and test-time compute scaling substantially enhances reasoning capabilities.

Country of Origin
🇦🇪 🇷🇺 United Arab Emirates, Russian Federation

Page Count
22 pages

Category
Computer Science:
Machine Learning (CS)